Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0937. Min Range: -5.0937
Max Act: 5.0937. Min Act: -0.1700
Data Index: 6354326 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.9062. Min Act: -0.1700
Data Index: 349547 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.8750. Min Act: -0.1700
Data Index: 649765 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.8125. Min Act: -0.1700
Data Index: 2499249 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.7500. Min Act: -0.1700
Data Index: 349549 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.7500. Min Act: -0.1700
Data Index: 1075323 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6875. Min Act: -0.1700
Data Index: 349546 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6562. Min Act: -0.1700
Data Index: 6610113 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6875. Min Act: -0.1700
Data Index: 7947047 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6875. Min Act: -0.1700
Data Index: 596425 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6562. Min Act: -0.1700
Data Index: 1328008 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6250. Min Act: -0.1700
Data Index: 6354327 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6562. Min Act: -0.1700
Data Index: 6208851 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6250. Min Act: -0.1700
Data Index: 1575503 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6562. Min Act: -0.1700
Data Index: 349548 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6250. Min Act: -0.1700
Data Index: 4003297 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.6250. Min Act: -0.1700
Data Index: 6934455 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.5937. Min Act: -0.1700
Data Index: 8208263 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.5937. Min Act: -0.1700
Data Index: 3255426 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0937. Min Range: -5.0937
Max Act: 4.5937. Min Act: -0.1700
Data Index: 4781528 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19